issue-triage
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue titles, bodies, and comments, which could serve as a vector for malicious instructions targeting the triage process.
- Ingestion points: The skill fetches issue details and full comment histories in SKILL.md (Phase 1 and Phase 2).
- Boundary markers: The prompt provided to the analysis subagents in SKILL.md does not include explicit delimiters or instructions to ignore embedded commands within the ingested issue content.
- Capability inventory: The skill utilizes the
ghCLI to perform actions such as posting comments, adding labels, and closing issues (Phase 3). - Sanitization: The risk is mitigated by a mandatory Phase 3 validation step, where the user must manually review and select which drafted actions to execute via the
AskUserQuestiontool.
Audit Metadata